V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-on-v-bench
SEAL
#17
Accuracy: 75.39
visual-question-answering-on-mm-vet
SEAL (7B)
#187
GPT-4 score: 27.7
Params: 7B
Rank counts only results with a code link.